© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6084
    Prev
    Next
    INDEX
    Explanations

    formulation and blends

    np_acts-logits-general · gemini-2.5-flash-lite

    materials and formulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    选举
    0.59
    简洁
    0.56
    批评
    0.56
     eingerichtet
    0.56
    aparikkh
    0.54
    联赛
    0.52
    文艺
    0.52
    惬
    0.52
    布局
    0.51
    .??.??"]
    0.51
    POSITIVE LOGITS
     formulations
    1.58
     formulation
    1.55
     Formulation
    1.33
     formulated
    1.31
     blends
    1.30
     resins
    1.30
     viscosity
    1.25
     formulating
    1.23
     polymer
    1.22
     resin
    1.19
    Activations Density 0.145%

    No Known Activations